Research map / 3D vision / Face and shape
Boundary-Aware 3D Building Reconstruction From a Single Overhead Image
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add BPSH prediction to Mask R-CNN (ablation) | building outline detection · SpaceNet | building outline F1: 65.0 -> 66.4 | Helped |
| Add TSDF prediction to Mask R-CNN (ablation) | building outline detection · GRSS DFC 2019 | building outline F1: 63.3 -> 62.7 | Hurt |
| Replace TSDF prediction with BPSH prediction (ablation) | building outline detection · SpaceNet and GRSS DFC 2019 | building outline F1: 65.6 -> 66.4; 62.7 -> 64.3 | Helped |
| Add semantic segmentation (ablation) | BPSH-based building outline detection · GRSS DFC 2019 | building outline F1: 64.3 -> 65.1 | Helped |
| Add height regression (ablation) | building outline detection with semantic segmentation · GRSS DFC 2019 | building outline F1: 65.1 -> 66.9 | Helped |
| Fuse auxiliary-task features into the detector at multiple scales (ablation) | building outline detection · GRSS DFC 2019 | building outline F1: 66.9 -> 67.5 | Helped |
| Use the full multi-task, multi-feature method rather than Wang & Frahm | building reconstruction · SpaceNet | building outline F1: 61.60 -> 68.87 | Helped |
| Use the full multi-task, multi-feature method rather than Wang & Frahm | building reconstruction · GRSS DFC 2019 | building outline F1: 57.86 -> 68.34 | Helped |
| Use the full method rather than Mou & Zhu | building height prediction · Urban 3D | pixelwise height MAE: 2.35 -> 2.34 | Helped |
Closest papers by meaning
- EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds (CVPR 2025 · similarity 0.86)
- 3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions (CVPR 2024 · similarity 0.85)
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (CVPR 2024 · similarity 0.85)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.85)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.85)
- ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.